Saved in:
Bibliographic Details
Main Authors: Goff, Théotime Le, Devijver, Émilie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.20481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908607107301376
author Goff, Théotime Le
Devijver, Émilie
author_facet Goff, Théotime Le
Devijver, Émilie
contents Out-of-distribution generalization is key to building models that remain reliable across diverse environments. Recent causality-based methods address this challenge by learning invariant causal relationships in the underlying data-generating process. Yet, measuring how causal structures differ across environments, and the resulting generalization difficulty, remains difficult. To tackle this challenge, we propose the Structural Causal Model Distance (SCMD), a principled metric that quantifies discrepancies between two SCMs by combining (i) kernel-based distances for nonparametric comparison of distributions and (ii) pairwise interventional comparisons to capture differences in causal effects. We show that SCMD is a proper metric and provide a consistent estimator with theoretical guarantees. Experiments on synthetic and real-world datasets demonstrate that SCMD effectively captures both structural and distributional differences between SCMs, providing a practical tool to assess causal transferability and generalization difficulty. Given two joint distributions P 1 (V j ) and P 2 (V j ), the Maximum Mean Discrepancy (MMD, Gretton et al. which defines a metric between distributions for characteristic kernels (Fukumizu et al., 2007). Kernel conditional mean embeddings (Park and Muandet, 2020) represent conditional expectation operators in an RKHS H Vj , which allows us to define the Maximum Conditional Mean Discrepancy between two
format Preprint
id arxiv_https___arxiv_org_abs_2510_20481
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SCMD: A Kernel-Based Distance for Structural Causal Models to Quantify Transferability Across Environments
Goff, Théotime Le
Devijver, Émilie
Statistics Theory
Out-of-distribution generalization is key to building models that remain reliable across diverse environments. Recent causality-based methods address this challenge by learning invariant causal relationships in the underlying data-generating process. Yet, measuring how causal structures differ across environments, and the resulting generalization difficulty, remains difficult. To tackle this challenge, we propose the Structural Causal Model Distance (SCMD), a principled metric that quantifies discrepancies between two SCMs by combining (i) kernel-based distances for nonparametric comparison of distributions and (ii) pairwise interventional comparisons to capture differences in causal effects. We show that SCMD is a proper metric and provide a consistent estimator with theoretical guarantees. Experiments on synthetic and real-world datasets demonstrate that SCMD effectively captures both structural and distributional differences between SCMs, providing a practical tool to assess causal transferability and generalization difficulty. Given two joint distributions P 1 (V j ) and P 2 (V j ), the Maximum Mean Discrepancy (MMD, Gretton et al. which defines a metric between distributions for characteristic kernels (Fukumizu et al., 2007). Kernel conditional mean embeddings (Park and Muandet, 2020) represent conditional expectation operators in an RKHS H Vj , which allows us to define the Maximum Conditional Mean Discrepancy between two
title SCMD: A Kernel-Based Distance for Structural Causal Models to Quantify Transferability Across Environments
topic Statistics Theory
url https://arxiv.org/abs/2510.20481